Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/LH8PPL/core-memory-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/lh8ppl/core-memory-kit/tour)<a href="https://agentmods.dev/commands/lh8ppl/core-memory-kit/tour"><img src="https://agentmods.dev/badge/commands/lh8ppl/core-memory-kit/tour/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/lh8ppl/core-memory-kit/tour"><img src="https://agentmods.dev/badge/commands/lh8ppl/core-memory-kit/tour.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00205 |
| Opus 5.5 | $0.00008 | $0.00082 |
| Sonnet 5.5 | $0.00004 | $0.00041 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
tour scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run cmk tour and present its output to the user conversationally.
Rules:
- Run the command; do NOT invent or embellish what the memory contains — the tour reads the user's real files, and your narration must stay faithful to its output (the kit's no-fabrication contract).
- Keep the presentation scannable: the tier table, what's captured (with the real examples the tour shows), how recall works, next steps.
- If the tour reports nothing captured yet, say so plainly and point at the
ways it fills (automatic capture, "remember this",
cmk import-sessions). cmk doctoris the health check; the tour is the explainer — if the user asks "is it working?", suggest doctor.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 19 lines · 21 tokens per session scan A e2f53c094377
tour is a command published in the GitHub repository LH8PPL/core-memory-kit (7 stars, last pushed 15d ago), licensed MIT. It adds 21 tokens to every session and 205 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
load
Load the shared Wingman context for this project.
tl-search
Search thoughtline memories by keyword or topickey GLOB.
remember
Save something to long-term local memory.
pickup
Pick up from a handoff snapshot: read a saved conversation state and continue from it, verifying against current ground truth before acting.
reflect
Synthesize patterns and a progress summary from milepost entries.